added lib version output

mwe.ipynb

@@ -2,23 +2,32 @@
  "cells": [
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 1,
    "id": "6942ccac",
    "metadata": {},
    "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/home/fredguth/.miniconda3/envs/py39/lib/python3.9/site-packages/torchvision/io/image.py:13: UserWarning: Failed to load image Python extension: /home/fredguth/.miniconda3/envs/py39/lib/python3.9/site-packages/torchvision/image.so: undefined symbol: _ZN3c104cuda20CUDACachingAllocator9allocatorE\n",
+      "  warn(f\"Failed to load image Python extension: {e}\")\n"
+     ]
+    },
     {
      "data": {
       "text/plain": [
        "'cuda'"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 1,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
     "import torch\n",
+    "\n",
     "from transformers import CLIPModel, CLIPVisionModel, CLIPProcessor\n",
     "from transformers import logging\n",
     "# Supress some unnecessary warnings when loading the CLIPTextModel\n",
@@ -40,6 +49,28 @@
   {
    "cell_type": "code",
    "execution_count": 7,
+   "id": "4813b77f",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'4.23.1'"
+      ]
+     },
+     "execution_count": 7,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "import transformers\n",
+    "transformers.__version__"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
    "id": "6591cd09",
    "metadata": {},
    "outputs": [],
@@ -51,10 +82,44 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 3,
    "id": "0a701777",
    "metadata": {},
-   "outputs": [],
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{'input_ids': tensor([[49406,   320,  1125,   539,  1237,  3989,  6982,   530,   320,  3360,\n",
+       "         15723, 49407]]), 'attention_mask': tensor([[1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]]), 'pixel_values': tensor([[[[ 0.5873,  0.5873,  0.6165,  ...,  0.0617,  0.0471, -0.0259],\n",
+       "          [ 0.5727,  0.5727,  0.6603,  ...,  0.1201,  0.0763,  0.0909],\n",
+       "          [ 0.5873,  0.5435,  0.6165,  ...,  0.0325,  0.1201,  0.0617],\n",
+       "          ...,\n",
+       "          [ 1.8719,  1.8573,  1.8719,  ...,  1.3902,  1.4340,  1.4194],\n",
+       "          [ 1.8281,  1.8719,  1.8427,  ...,  1.4486,  1.4340,  1.5070],\n",
+       "          [ 1.8573,  1.9011,  1.8281,  ...,  1.3756,  1.3610,  1.4486]],\n",
+       "\n",
+       "         [[-1.3169, -1.3019, -1.3169,  ..., -1.4970, -1.4369, -1.4820],\n",
+       "          [-1.2418, -1.2718, -1.2268,  ..., -1.4369, -1.4669, -1.4519],\n",
+       "          [-1.2568, -1.3169, -1.2268,  ..., -1.4669, -1.4069, -1.4519],\n",
+       "          ...,\n",
+       "          [ 0.1239,  0.1089,  0.1239,  ..., -0.7016, -0.6865, -0.6865],\n",
+       "          [ 0.0789,  0.0939,  0.0488,  ..., -0.6565, -0.6865, -0.6115],\n",
+       "          [ 0.0939,  0.1089,  0.0038,  ..., -0.7766, -0.7316, -0.6115]],\n",
+       "\n",
+       "         [[-0.4848, -0.4137, -0.3853,  ..., -0.9541, -0.8545, -0.8545],\n",
+       "          [-0.4137, -0.4706, -0.3711,  ..., -0.8119, -0.8545, -0.7834],\n",
+       "          [-0.3284, -0.4422, -0.3853,  ..., -0.8688, -0.8119, -0.8830],\n",
+       "          ...,\n",
+       "          [ 1.5771,  1.6482,  1.6340,  ...,  0.9088,  0.9514,  0.8945],\n",
+       "          [ 1.6198,  1.6055,  1.6055,  ...,  0.8661,  0.8092,  0.7950],\n",
+       "          [ 1.6624,  1.6766,  1.5487,  ...,  0.7950,  0.8661,  0.8519]]]])}"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
    "source": [
     "url = \"http://images.cocodataset.org/val2017/000000039769.jpg\"\n",
     "image = Image.open(requests.get(url, stream=True).raw)\n",
@@ -64,23 +129,17 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 4,
    "id": "e148125e",
    "metadata": {},
    "outputs": [
     {
      "data": {
       "text/plain": [
-       "BaseModelOutputWithPooling(last_hidden_state=tensor([[[-0.5297, -0.7713,  0.4655,  ..., -0.3993, -0.0721, -0.3703],\n",
-       "         [ 0.8688,  0.1690,  0.6678,  ...,  0.5126, -1.1465, -0.1258],\n",
-       "         [ 1.1742, -0.7551,  0.0396,  ...,  0.7166, -0.5458,  0.0031],\n",
-       "         ...,\n",
-       "         [ 0.8636,  0.2223,  0.6411,  ...,  0.5242, -0.8104,  0.0170],\n",
-       "         [ 0.6842, -1.1056, -0.2486,  ...,  0.7901,  0.4862, -0.0949],\n",
-       "         [ 0.8934,  0.0066,  0.9235,  ...,  0.5707, -0.8436, -0.2182]]]), pooler_output=tensor([[-0.9326, -1.3289,  0.7919,  ..., -0.3337, -0.0479, -0.7106]]), hidden_states=None, attentions=None)"
+       "(torch.Size([1, 257, 1024]), torch.Size([1, 12, 768]))"
       ]
      },
-     "execution_count": 19,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -94,7 +153,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 22,
+   "execution_count": 5,
    "id": "f28bb4b6",
    "metadata": {},
    "outputs": [
@@ -121,7 +180,7 @@
        "}"
       ]
      },
-     "execution_count": 22,
+     "execution_count": 5,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -132,7 +191,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 6,
    "id": "6726b263",
    "metadata": {},
    "outputs": [
@@ -161,7 +220,7 @@
        "}"
       ]
      },
-     "execution_count": 23,
+     "execution_count": 6,
      "metadata": {},
      "output_type": "execute_result"
     }